INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Abstract— Today's age put a significant amount of emphasis on monitoring systems. It has received a lot of research recently due to its connection to picture understanding and video analysis. More effective tools that can extract high information content are introduced into the system when artificial intelligence, deep learning, and machine learning are integrated to address the issues with standard style. Most anomaly detection tools focus on indoor surveillance and activity monitoring, which help identify abnormal behavior by watching the live stream footage. The most important of them all is the detection of human nature. It is the most strange behavior, which makes it difficult to assess whether it is normal or suspicious. This study demonstrates how in-depth learning can be used to spot odd behaviour on college or high school campuses. Employing consecutive camera frames obtained from a video, the monitoring is done. We will use our model to find the abnormal behaviour in the extracted camera frames. As soon as an anomaly is found, the stream is saved, alerting the relevant people. Therefore, we only need to save the portion of the video where the anomaly is occurring, rather than recording the entire feed. The system is composed of two parts. In the first section, features will be computed from the live video stream, and the classifier will use those features to forecast the anomaly in the second section. The proposed system can recognize the anomalies with a loss of 4.795.
Keywords— LSTM, CNN, Autoencoders, Reconstruction error, Regularity Score
Keywords:
Anomaly Detection , CNN
Cite Article:
"Real-Time Anomaly Detection Surveillance System", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 6, page no.d566-d572, June-2023, Available :http://www.ijnrd.org/papers/IJNRD2306358.pdf
Downloads:
000118762
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn